Papers with hyper-parameter tuning

11 papers
Domain Adaptation with BERT-based Domain Classification and Data Selection (D19-61)

Copied to clipboard

Challenge: Modern deep neural models with millions of parameters can easily adapt to a new learning task and dataset when enough supervision is given.
Approach: They propose a domain adaptation framework based on curriculum learning and domain-discriminative data selection.
Outcome: The proposed framework outperforms discrepancy-based methods on transfer tasks while consuming only fraction of training budget.
Azimuth: Systematic Error Analysis for Text Classification (2022.emnlp-demos)

Copied to clipboard

Challenge: Azimuth is an open-source tool to perform error analysis for text classification.
Approach: They propose an open-source tool to perform error analysis for text classification . they propose to combine a range of ML techniques to facilitate the error analysis stage .
Outcome: The proposed approach helps AI practitioners discover and address areas where the model does not generalize by leveraging and integrating a range of ML techniques.
DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations (2022.acl-long)

Copied to clipboard

Challenge: Existing evaluation metrics for incoherent dialogues are insufficient to accurately reflect incohérence . despite the effectiveness of large pretrained language models, not everyone is into this type of work.
Approach: They propose a Dialogue coherence Evaluation metric that uses Abstract Meaning Representation to apply semantic-level Manipulations for incoherent (negative) data generation.
Outcome: The proposed evaluation metric achieves higher correlations with human judgments compared to baseline methods on dialog datasets by significant margins.
A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignment (2023.findings-acl)

Copied to clipboard

Challenge: Entity alignment is the task of identifying corresponding entities across different knowledge graphs (KGs).
Approach: They propose an unsupervised entity alignment framework that leverages the Fused Gromov-Wasserstein distance to compare KG semantics and KG structural information.
Outcome: The proposed framework surpasses 21 competitive baselines, including cutting-edge methods, without supervision or hyper-parameter tuning.
AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in Large Language Models have transformed ML/AI development . a reevaluation of AutoML principles for Retrieval-Augmented Generation (RAG) systems is needed.
Approach: They propose a framework for hyper-parameter tuning and a hierarchical MAB method for efficient exploration of large search spaces.
Outcome: The proposed framework outperforms baseline methods in more challenging optimization scenarios.
AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning (N19-1)

Copied to clipboard

Challenge: Multi-task learning is an inductive transfer mechanism that leverages information from related tasks to improve the primary model's generalization performance.
Approach: They propose a multitask learning pipeline that finds relevant auxiliary tasks and learns their mixing ratio.
Outcome: The proposed model can find relevant auxiliary tasks and learn their mixing ratio . the proposed model achieves significant performance boosts on several primary tasks .
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data (2024.findings-emnlp)

Copied to clipboard

Challenge: Reinforcement Learning from Human Feedback (RLHF) relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and pose challenges in sample efficiency and stability.
Approach: They propose an innovative framework that leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model’s responses.
Outcome: The proposed framework matches and exceeds the effectiveness of Proximal Policy Optimization (PPO) in terms of convergence speed and alignment of model responses with human preferences.
Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks (P19-1)

Copied to clipboard

Challenge: Existing approaches for text classification are lexicallevel features with Naive Bayes or Support Vector Machines (SVM) .
Approach: They propose a deep-learning model that uses label descriptions to train texts and their labels for multi-label and multi-class classification tasks.
Outcome: The proposed model improves on one set with a high margin and on all other sets with competitive results.
Robustness of Named-Entity Replacements for In-Context Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: Modern large language models perform in-context learning, where query- answer demonstrations are shown before the final query.
Approach: They propose to use in-context learning to prompt queries before they are answered . they find that the choice of demonstrations can affect model performance .
Outcome: The proposed model performance improves on named entity replacements across three reasoning tasks and two popular LLMs.
Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification (2024.findings-emnlp)

Copied to clipboard

Challenge: Prior research has shown that pretrained language models (PLMs) can achieve state-of-the-art performance on CIC benchmarks.
Approach: They propose a multi-task learning framework that fine-tunes pretrained language models on a dataset of primary interest together with multiple auxiliary CIC datasets to take advantage of additional supervision signals.
Outcome: The proposed framework outperforms current state-of-the-art models on small datasets while aligning with the best-performing model on a large dataset.
Towards Aligning Language Models with Textual Feedback (2024.emnlp-main)

Copied to clipboard

Challenge: Using textual feedback, language models can be trained to learn from textual inputs.
Approach: They propose an approach that aligns language models with user preferences expressed in text.
Outcome: The proposed approach outperforms PPO on toxicity reduction, summarization, and dialog response tasks while achieving the same performance with only 20% of the samples.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations